coordinator-response-mode

Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is Response Mode. This skill contains the complete decision table, exemplar prompts for each mode, the Lightweight spawn template, and the upgrade rules. Squad coordinator loads this on demand once routing has identified the agent — to pick the right ceremony level for the task.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable decision skill: the mode table, exemplars, upgrade rules, and complete spawn template give the coordinator everything needed with no padding. Its only weaknesses are minor — a redundant load-when blockquote and a body slightly long enough that some content could move to a reference file.

Dimension	Reasoning	Score
Conciseness	Efficient throughout — a dense decision table, terse exemplar lists, and no explanations of concepts Claude already knows. Not 5: the opening blockquote ('Load this skill when...') duplicates the frontmatter description, and the spawn template carries boilerplate that could be trimmed.	4 / 5
Actionability	Fully actionable: the mode table gives When/How/Target per mode, exemplars include a real command ('git branch --show-current'), and the Lightweight spawn template is complete and copy-paste ready including the read-only explore-agent variant. Placeholders are template variables by design, not pseudocode.	5 / 5
Workflow Clarity	The single action — pick a mode — is unambiguous: the selection table plus explicit tie-breaker upgrade rules ('If uncertain between Lightweight and Standard → choose Standard', 'Never downgrade mid-task') serve as decision checkpoints. Per the simple-skill note, a single unambiguous action can score 5; no destructive or batch operations apply the validation cap.	5 / 5
Progressive Disclosure	Scored against the actual bundle structure: no references/, scripts/, or assets/ directories exist, so the skill is deliberately self-contained with flat, clearly headed sections and a one-line pointer to the upstream stub in squad.agent.md. Not 5: the body exceeds 50 lines, and the per-mode exemplars and spawn template could arguably be split into a reference file, though inline is defensible for an on-demand satellite skill.	4 / 5
	Total	18 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly delimits its scope against the Routing table, names its concrete contents, and states when the coordinator should load it. It is inventory- and jargon-leaning rather than action- and trigger-phrase-leaning, which keeps it just below the top anchors.

Suggestions

Lead with an action verb describing what the skill does (e.g., 'Selects the response mode...') rather than opening with the WHO/HOW definitional distinction.

Add an explicit 'Use when...' clause with natural trigger phrases a user or coordinator would say (e.g., 'Use when deciding between Direct, Lightweight, Standard, or Full response after routing').

Reduce reliance on internal jargon like 'ceremony level' or pair it with a plainer synonym to broaden natural trigger matching.

Dimension	Reasoning	Score
Specificity	Names several concrete contents — 'the complete decision table, exemplar prompts for each mode, the Lightweight spawn template, and the upgrade rules' — matching 'lists several specific actions; minor gaps.' It falls short of 5 because the framing is inventory-style ('This skill contains...') rather than comprehensive action verbs, and the opening WHO/HOW clause is definitional context.	4 / 5
Completeness	Both are present: what ('complete decision table, exemplar prompts... upgrade rules') and when ('loads this on demand once routing has identified the agent'). Not 5 because the 'when' is coordinator-internal rather than concrete user-facing trigger phrases; not 3 because explicit trigger guidance exists, so the missing-'Use when' cap does not apply.	4 / 5
Trigger Term Quality	Good keyword coverage: all four mode names (Direct, Lightweight, Standard, Full), 'routing', 'spawn', and 'coordinator' are natural terms for the domain. Below 5 because common synonyms a user might say (e.g., 'delegate', 'how should the agent respond') are missing and 'ceremony level' is internal jargon.	4 / 5
Distinctiveness Conflict Risk	The description explicitly carves its niche against the nearest neighbor — 'Selecting WHO handles work is the Routing table; selecting HOW they handle it... is Response Mode' — giving it distinct triggers and minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .squad-templates/skills/coordinator-response-mode/SKILL.md
Commit: 29e69f5

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.